Thanks to visit codestin.com
Credit goes to github.com

Skip to content

Tags: artyom/llmcli

Tags

v0.5.1

Toggle v0.5.1's commit message
LLMCLI_MUTE_THINKING=1 suppresses reasoning text

v0.5.0

Toggle v0.5.0's commit message
Fallback to Converse API for models without streaming support

v0.4.6

Toggle v0.4.6's commit message
Allow “thinking” and prompt caching on Claude 4 models

v0.4.5

Toggle v0.4.5's commit message
Cache system prompt if possible

v0.4.4

Toggle v0.4.4's commit message
Improve terminal detection and escape sequence handling

Replace custom terminal detection with golang.org/x/term library.

v0.4.3

Toggle v0.4.3's commit message
Lift formatting out of Chunks method

Chunks method now returns richer type that allows to distinguish between
“thinking” and regular response text. Output stream formatting now
happens within the Chunks method caller code.

While here, also make sure that ansi escape codes are only printed to
stdout, they are not written to the buffer used to accumulate markdown
to be later rendered into html.

v0.4.2

Toggle v0.4.2's commit message
Improve Claude 3.7 thinking budget validation

Consolidate logic within the flag parsing function.

v0.4.1

Toggle v0.4.1's commit message
Format Claude 3.7 “thinking” output differently

v0.4.0

Toggle v0.4.0's commit message
Support “extended thinking” mode of Claude 3.7 Sonnet

v0.3.0

Toggle v0.3.0's commit message
Use full filename (as provided) when sending text attachments